Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3211 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.5745. Min Act: -0.0000

Data Index: 920109 (C4 (Web Text))

Max Activating Token Index: 105

Text #1

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4757. Min Act: -0.0000

Data Index: 225319 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4476. Min Act: -0.0000

Data Index: 346659 (C4 (Web Text))

Max Activating Token Index: 267

Text #3

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4777. Min Act: -0.0000

Data Index: 1141358 (C4 (Web Text))

Max Activating Token Index: 70

Text #4

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4175. Min Act: -0.0000

Data Index: 506376 (C4 (Web Text))

Max Activating Token Index: 730

Text #5

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4235. Min Act: -0.0000

Data Index: 1185793 (C4 (Web Text))

Max Activating Token Index: 939

Text #6

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4206. Min Act: -0.0000

Data Index: 237085 (C4 (Web Text))

Max Activating Token Index: 7

Text #7

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4194. Min Act: -0.0000

Data Index: 1274958 (C4 (Web Text))

Max Activating Token Index: 466

Text #8

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4297. Min Act: -0.0000

Data Index: 986047 (C4 (Web Text))

Max Activating Token Index: 72

Text #9

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4272. Min Act: -0.0000

Data Index: 1216507 (C4 (Web Text))

Max Activating Token Index: 7

Text #10

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4142. Min Act: -0.0000

Data Index: 193885 (C4 (Web Text))

Max Activating Token Index: 187

Text #11

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4010. Min Act: -0.0000

Data Index: 657916 (C4 (Web Text))

Max Activating Token Index: 788

Text #12

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4010. Min Act: -0.0000

Data Index: 880145 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4154. Min Act: -0.0000

Data Index: 136930 (C4 (Web Text))

Max Activating Token Index: 21

Text #14

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4171. Min Act: -0.0000

Data Index: 102148 (C4 (Web Text))

Max Activating Token Index: 991

Text #15

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4022. Min Act: -0.0000

Data Index: 709380 (C4 (Web Text))

Max Activating Token Index: 928

Text #16

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4101. Min Act: -0.0000

Data Index: 602447 (C4 (Web Text))

Max Activating Token Index: 314

Text #17

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4077. Min Act: -0.0000

Data Index: 112007 (C4 (Web Text))

Max Activating Token Index: 512

Text #18

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.3936. Min Act: -0.0000

Data Index: 959444 (C4 (Web Text))

Max Activating Token Index: 817

Text #19

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.3889. Min Act: -0.0000

Data Index: 9108 (C4 (Web Text))

Max Activating Token Index: 419